MASA: Motion-Aware Masked Autoencoder With Semantic Alignment for Sign Language Recognition

Sign language recognition (SLR) has long been plagued by insufficient model representation capabilities. Although current pre-training approaches have alleviated this dilemma to some extent and yielded promising performance by employing various pretext tasks on sign pose data, these methods still su...

Full description

Bibliographic Details

Published in:	IEEE transactions on circuits and systems for video technology Vol. 34; no. 11; pp. 10793 - 10804
Main Authors:	Zhao, Weichao, Hu, Hezhen, Zhou, Wengang, Mao, Yunyao, Wang, Min, Li, Houqiang
Format:	Journal Article
Language:	English
Published:	IEEE 01.11.2024
Subjects:	Assistive technologies Feature extraction Masked autoencoder motion-aware Representation learning Self-supervised learning semantic alignment Semantics Sign language sign language recognition Task analysis
ISSN:	1051-8215, 1558-2205
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!